Skip to main content
ARS Home » Midwest Area » St. Paul, Minnesota » Plant Science Research » Research » Publications at this Location » Publication #410170
Research Project: Genetic Improvement and Cropping Systems of Alfalfa for Livestock Utilization, Environmental Protection and Soil Health

Location: Plant Science Research

Title: Editorial: Machine vision and machine learning for plant phenotyping and precision agriculture

Author
item LIU, HUAJIAN - University Of Adelaide
item Xu, Zhanyou

Submitted to: Frontiers in Plant Science
Publication Type: Review Article
Publication Acceptance Date: 11/17/2023
Publication Date: 11/27/2023
Citation: Liu, H., Xu, Z. 2023. Editorial: Machine vision and machine learning for plant phenotyping and precision agriculture. Frontiers in Plant Science. 14. Article 1331918. https://doi.org/10.3389/fpls.2023.1331918.
DOI: https://doi.org/10.3389/fpls.2023.1331918

Interpretive Summary: The improvement of plant breeding depends on the accuracy and efficiency of measuring agronomic traits. Traditionally, agronomic trait collection heavily relies on domain experts, which is labor-intensive, time-consuming, and subjective. Recently, driven by computer and sensor technologies, machine vision (MV), machine learning (ML), and deep learning have contributed to accurate, high-throughput, and nondestructive plant phenotyping and precision agriculture. However, these technologies are still in their early stage of development for large-scale application, and many related challenges and questions still need to be addressed. The specific topic "Machine Vision and Machine Learning for Plant Phenotyping and Precision Agriculture" of Frontiers in Plant Science has published 28 reports associated with applying machine learning for plant phenotyping and precision agriculture in the past year. This article summarized the progress, challenges, and future research perspectives, providing introductive information for artificial intelligence (AI) model developers, researchers, and breeders.

Technical Abstract: The genetic gain of plant breeding depends on the accuracy and efficiency of agronomic trait-taking. Traditionally, agronomic trait collection heavily relies on domain experts, which is labor-intensive, time-consuming, and subjective. Recently, driven by computer and sensor technologies, machine vision (MV), machine learning (ML), and deep learning have contributed to accurate, high-throughput, and nondestructive plant phenotyping and precision agriculture. However, these technologies are still in their early stage of development for large-scale application, and many related challenges and questions still need to be addressed. The specific topic "Machine Vision and Machine Learning for Plant Phenotyping and Precision Agriculture" of Frontiers in Plant Science has published 28 reports associated with applying machine learning for plant phenotyping and precision agriculture in the past year. This editorial summarized the progress, challenges, and future research perspectives, providing introductive information for artificial intelligence (AI) model developers, researchers, and breeders.